Interactive Learning and Analogical Chaining for Moral and Commonsense Reasoning
Authors: Joseph Blass
AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Work is progressing on RAC for commonsense reasoning. We are selecting a subset of training questions from the COPA (Roemmele et al., 2011) corpus of commonsense questions. We will encode CSUs relevant to solving these questions, then show that RAC can repeatedly find relevant CSUs and apply them in order to solve these questions. |
| Researcher Affiliation | Academia | Joseph A. Blass Qualitative Reasoning Group, Northwestern University, Evanston, IL joeblass@u.northwestern.edu |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described, nor does it state that the code will be made available. |
| Open Datasets | Yes | We are selecting a subset of training questions from the COPA (Roemmele et al., 2011) corpus of commonsense questions. |
| Dataset Splits | No | The paper mentions using the COPA corpus but does not provide specific dataset split information (e.g., percentages, sample counts, or citations to predefined splits) needed to reproduce the data partitioning. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper mentions systems like 'QRG s NLU system, EA NLU' and resources like 'The Moral Foundations Dictionary' but does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers) needed to replicate the experiment. |
| Experiment Setup | No | The paper describes the conceptual design and intended functionality of the system but does not contain specific experimental setup details such as concrete hyperparameter values, training configurations, or system-level settings. |